JP2015114757A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent the loss of visibility when displaying overlaid images of AR.SOLUTION: An information processing apparatus includes an imaging unit, a control unit, and an output unit. The control unit is configured to detect a candidate area for overlaid display of content, from an image imaged by the imaging unit. The control unit is further configured to detect, as an overlaid display area, out of the candidate area, an area where a change in undulation of luminance distribution is equal to or less than a threshold value. The control unit is further configured to generate the content to be arranged virtually in a visually recognizable manner on the overlaid display area, to be recognized by a user. The output unit is configured to output the generated content overlaid on the overlaid display area.

Description

  The present technology relates to an information processing apparatus capable of displaying content superimposed on an input image, an information processing method in the information processing apparatus, and a program.

  In recent years, research on Mixed Reality (MR), which is an environment that combines real space and virtual space, has been actively conducted. Among them, the reality is realized by superimposing virtual space contents on real space. AR (Augmented Reality), which enhances the sense of sensation, has attracted attention.

  The AR has already been realized in wearable devices such as smartphones, HMDs (Head Mount Displays), and see-through glasses. For example, in the following Patent Document 1, in a portable terminal device possessed by a visitor who walks around the ruins, information on the exhibits in the ruins is superimposed and displayed on a live-action image taken by the camera. Technology is disclosed.

JP 2011-252879 A

  However, in the conventional technique such as Patent Document 1, the visibility of the virtual content is impaired when, for example, the texture component in the superimposed display area of the virtual content is strong on the image captured by the camera. There was a problem.

  In view of the circumstances as described above, an object of the present technology is to provide an information processing device, an information processing method, and a program capable of preventing visibility from being impaired in superimposed display by AR.

  In order to solve the above-described problem, an information processing apparatus according to an embodiment of the present technology includes an imaging unit, a control unit, and an output unit. The control unit detects a candidate region that is a candidate for superimposed display of content from the image captured by the imaging unit, and superimposes the region where the undulation change of the luminance distribution is equal to or less than a first threshold among the candidate regions. And the content is arranged so as to be virtually viewed on the superimposed display area by the user. The output unit is configured to output the generated content superimposed on the superimposed display area.

  As a result, the information processing apparatus detects an area where the undulation change of the luminance distribution is small, that is, an area where the texture is weak and superimposes the content. Can be prevented.

  The control unit may detect, as the superimposed display area, an area in which the undulation change of the three-dimensional shape is equal to or less than a second threshold among the candidate areas.

  Thereby, the information processing apparatus can display the content with high visibility in a form along the shape of the real world by detecting the flat area as the superimposed display area.

  The control unit may detect whether the candidate area is a moving object area from the input image and exclude the moving object area from the superimposed display area.

  Accordingly, the information processing apparatus can improve not only the visibility but also the safety by preventing the content from being displayed in the moving object region.

  You may further comprise the sensor comprised so that the attitude | position of the said information processing apparatus might be detected. In this case, the control unit may detect a change in posture detected by the sensor, and detect the moving object region by subtracting the change in posture from the input image.

  Accordingly, the information processing apparatus can detect the moving object region in the image with high accuracy even during the movement of the apparatus by canceling the influence of the change in the posture.

  The control unit calculates a first depth distribution and a second depth distribution from a continuous first image and second image among the input images, and the first image and the second image are calculated. The third depth distribution is calculated by reflecting the variation amount of the posture detected in the time interval in the first depth distribution, and whether there is a difference between the second depth distribution and the third depth distribution. By detecting this, the presence or absence of the moving object region may be detected.

  Thereby, the information processing apparatus can detect the moving object region in the image with high accuracy by moving the apparatus by comparing the depth distribution between the frames by shifting the amount of the posture variation.

  You may further comprise the sensor which detects the attitude | position of the said information processing apparatus. In this case, the control unit determines whether or not the information processing apparatus is stationary based on the detection result of the sensor. When the information processing apparatus is stationary, the control unit The moving object region may be detected by extracting the difference.

  Accordingly, the information processing apparatus can reduce the processing load by simplifying the detection of the moving object region by limiting the superimposed display process only to the stationary state.

  The output unit may output the generated content superimposed on the superimposed display area in a semi-transparent state. In this case, when the candidate area whose undulation change of the luminance distribution is not more than a first threshold is not detected, the control unit is configured to superimpose the generated content so that the transparency of the generated content is lower than that of the semi-transparent state. The output unit may be controlled.

  As a result, the information processing apparatus can prevent degradation of visibility and safety by lowering the content transparency when an area with a weak texture is not found.

  When the candidate area whose undulation change of the luminance distribution is less than or equal to a first threshold is not detected, the control unit determines that the content is changed to an area other than the candidate area, and the undulation change of the luminance distribution is greater than the first threshold. The output unit may be controlled so as to be displayed in association with a large candidate area.

  As a result, even when an area with a weak texture is not found, the information processing apparatus displays the content in an area other than the candidate area, for example, with a leader line from the candidate area, thereby allowing the user to relate the relationship between the area and the content. It can be grasped.

  The control unit may detect a moving object region as the superimposed display region from the input image.

  Thus, the information processing apparatus can attract the user's interest by setting the moving object as a content overlapping display area.

An information processing method according to another aspect of the present technology is as follows:
Detecting a candidate region that is a candidate for superimposed display of content from an image captured and input by an imaging device;
Detecting a region where the undulation change of the luminance distribution is equal to or less than a predetermined threshold among the detected candidate regions as a superimposed display region;
Generating the content arranged to be virtually viewed by the user on the superimposed display area; and
Including superimposing the generated content on the superimposed display area and outputting the superimposed content.

A program according to another embodiment of the present technology is provided in an information processing device.
Detecting a candidate region that is a candidate for superimposed display of content from an image captured and input by an imaging device;
A step of detecting, as a superimposed display region, a region where the undulation change of the luminance distribution is not more than a predetermined threshold among the detected candidate regions;
Generating the content arranged to be virtually viewed by the user on the superimposed display area;
And outputting the generated content superimposed on the superimposed display area.

  As described above, according to the present technology, it is possible to prevent the visibility from being impaired in the superimposed display by AR. However, this effect does not limit the present technology.

It is a figure showing an outline of a system using HMD concerning one embodiment of this art. It is the block diagram which showed the hardware constitutions of the said HMD. It is the flowchart which showed the flow of the content superimposition display process of the said HMD. It is the flowchart which showed the detailed flow of the detection process of the moving body area | region in the content superimposition display process of the said HMD.

  Hereinafter, embodiments according to the present technology will be described with reference to the drawings.

[System Overview]
FIG. 1 is a diagram illustrating an overview of a system according to an embodiment of the present technology.

  As shown in the figure, in the present embodiment, an AR environment is realized by a user wearing a see-through glasses type HMD (Head Mount Display) 100 on the head. While visually recognizing the real environment through the lens (display unit) of the HMD 100, the user can visually recognize the content C that is virtually displayed superimposed on a road, a building, a signboard, or the like in the real environment.

  For example, as shown in the figure, when viewed from the user, a line for navigating the route to the user's destination is displayed on the road, and information on restaurants and bars existing in the building is displayed on the building. It is displayed.

  In the present embodiment, when performing the superimposed display in the AR system, the HMD 100 displays the content in a superimposed manner while avoiding a region having a strong texture (a large change in the undulation of the luminance distribution) in view of the user's visibility. It is possible.

[HMD hardware configuration]
FIG. 2 is a block diagram showing a hardware configuration of the HMD 100. As shown in FIG.

  As shown in the figure, the HMD 100 includes a control unit 11, a storage unit 12, a communication unit 13, a sensor unit 14, an operation reception unit 15, a right camera 16, a left camera 17, and a display unit 18.

  The control unit 11 includes, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and the like, and comprehensively controls each block of the HMD 100 while performing various arithmetic processes in a superimposed display process of content.

  The storage unit 12 is a non-volatile memory such as a flash memory (SSD; Solid State Drive) or other solid-state memory. The storage unit 12 stores an OS, various applications, and various data. In particular, in the present embodiment, the storage unit 12 stores, for example, superimposed display target content (for example, advertising text or images).

  The communication unit 13 is a wireless communication module corresponding to a standard such as a wireless local area network (WiFi) such as WiFi (Wireless Fidelity) or Bluetooth (registered trademark), and can communicate with a device such as a smartphone carried by the user, for example. It is said that. The communication unit 13 can receive data necessary for superimposed display of content, map information, and the like via a user's portable device such as a smartphone or directly from the Internet.

  The sensor unit 14 includes various sensors such as a gyro sensor, an acceleration sensor, and a geomagnetic sensor, and detects the orientation, position, direction, and the like of the HMD 100 (user) for display processing of the virtual three-dimensional object O.

  The operation reception unit 15 includes, for example, a touch panel, buttons, switches, and the like, and receives various user operations.

  The right camera 16 and the left camera 17 are provided, for example, in the right frame and the left frame of the HMD 100, respectively, and from the parallax between images captured by both, the real environment in front of the user (object position, stereoscopic shape and depth ( Depth Map)) functions as a stereo camera.

  The display unit 18 is configured as a transmissive display, and includes a display element 181 and an optical member 182. For example, the display unit 18 forms an image of content by the display element 181 housed in the frame unit of the HMD 100, guides the image light into the optical member 182, and emits the image of the content to the eyes of the user. Present to the user. The content image may be a two-dimensional image or a three-dimensional image.

  The display element 181 is configured by an LCD (Liquid Crystal Display), for example. The optical member 182 includes a deflecting element (hologram diffraction grating) and a light guide plate as a display surface, and light having a specific wavelength corresponding to each color of RGB is diffracted and reflected by the polarizing element and totally reflected in the light guide plate. The image is emitted to the user's eyes.

[Operation of HMD]
Next, the operation of the HMD 100 configured as described above will be described. In the following description, the control unit 11 of the HMD will be described as the main operating subject, but this operation is performed in cooperation with other hardware and software executed under the control of the control unit 11.

(Superimposed display processing)
FIG. 3 is a flowchart showing a flow of content superimposition display processing of the HMD 100.

  As shown in the figure, first, an image group captured by the right camera 16 and the left camera 17 is input to the control unit 11 of the HMD 100 (step 31). The input image group may be from one camera.

  Subsequently, the control unit 11 recognizes real environment information in which the user exists from the input image (step 32).

  Specifically, the control unit 11 estimates and calculates the postures of the cameras 16 and 17 for each input image. The postures of the cameras 16 and 17 are composed of positions and angles in the three-dimensional world (directions in which the cameras 16 and 17 are facing). These can be obtained, for example, from pixel value and feature point matching results between images, information from the sensor unit 14 (acceleration sensor / angular velocity (gyro) sensor, geomagnetic sensor), and the like.

  Further, the control unit 11 may additionally calculate depth information (DepthMap). The depth information is obtained by matching a plurality of images such as a plurality of time-series frames or a pair of stereo images input from the cameras 16 and 17. Also, a method of using another sensor, such as irradiating an IR pattern with an IR sensor, can be applied.

  Furthermore, the control unit 11 can recognize an actual environment by recognizing an object from an image or using GPS information.

  Subsequently, based on the recognition result of the real environment, the control unit 11 determines the content to be superimposed and the candidate area for the superimposed display, such as various information associated with the advertisement and the map information, according to the request and context from the user. (Step 33).

  In selecting the superimposed display candidate area, the control unit 11 may detect the user's line of sight. The user's line of sight may be detected by the right camera 16 and the left camera 17, for example, a dedicated sensor such as a near infrared LED (Light Emitting Diode) sensor capable of detecting the user's pupil or a combination of the sensor and the camera, It may be detected by other optical / physical / electrical methods.

  Subsequently, the control unit 11 analyzes the image of the superimposed display candidate area and determines whether it is suitable as the superimposed area (step 34).

  Specifically, the control unit 11 detects whether the superimposed display candidate area is a moving object area, a texture area, or a non-planar area (step 35), and the superimposed display candidate area meets these three conditions. If so, the region is excluded from the candidates (step 36).

  The moving object area corresponds to, for example, a crowd or a street of a car. The control unit 11 can detect whether there is a moving object on the subject side after subtracting fluctuations in the postures of the cameras 16 and 17. The reason why the moving object region is excluded from the superimposed display candidates is that there is a problem not only in terms of visibility but also in terms of safety. Details of the moving object region detection method will be described later.

  The texture region is a region where the undulation change of the luminance distribution is severe. The control unit 11 can detect the texture region by determining whether or not the texture is strong from a distribution such as luminance dispersion within the rectangular region of the input image.

  For example, when the undulation change in the luminance distribution of the superimposed display candidate region exceeds a predetermined threshold, the control unit 11 excludes the region from the superimposed display candidate. That is, an area where the undulation change of the luminance distribution is equal to or less than the threshold value is detected as a superimposed display area.

  As described above, the HMD 100 is a see-through spectacle type device, and from the viewpoint of visibility and safety, it is considered that the superimposed display is basically performed in a semi-transparent manner, so that the texture component is strong, that is, the region is highly dispersed. Superimposition should be avoided.

  The non-planar region is a region where the distribution of the three-dimensional shape is not flat. For example, an area having a flat shape, such as a wall, a floor, or a hollow space, is suitable as an overlapping area because the content to be superimposed can be displayed along the shape in the real world.

  As described above, the non-planar region (planar region) may be detected by a passive depth information acquisition method by matching a plurality of images, such as the stereo images of the cameras 16 and 17 and a plurality of time-series frames, or by a sensor. It may be detected by an active depth information acquisition method by IR pattern irradiation or the like.

  For example, when the undulation change of the three-dimensional shape distribution of the superimposed display candidate region exceeds a predetermined threshold (different from the threshold value of the texture region), the control unit 11 excludes the region from the superimposed display candidate. . That is, an area where the undulation change of the distribution of the three-dimensional recording is equal to or less than the threshold is detected as the superimposed display area.

  Subsequently, the control unit 11 determines whether or not there is an area that can be superimposed and displayed after the above determination and exclusion from the candidate area (step 37).

  When it determines with the area | region which can be superimposed displayed existing (No), the control part 11 determines the said area | region as a superimposed display area, the content associated with it is produced | generated in the display part 18, and it superimposes on the said area | region. Display (step 39).

  When it determines with the area | region which can be superimposed displayed not existing (Yes), the control part 11 determines an area | region which is areas other than a superimposed display candidate area | region, and does not correspond to the said exclusion criteria as a superimposed display area (step 38). ).

  And the control part 11 superimposes and displays a content on area | regions other than the said candidate area | region (step 39). At this time, for example, the control unit 11 displays a line segment from the excluded candidate area to the superimposed display area, or displays content in a balloon shape from the excluded candidate area to indicate the association between the areas. Also good.

  In addition, when a superimposed display area other than the candidate area is not found, the control unit 11 may superimpose and display content whose transparency is lower than a normal value on the detected texture area or non-planar area. .

  The control unit 11 can superimpose and display various contents in an area that is highly visible to the user and does not obstruct the field of view according to the various determination criteria as described above.

(Moving object detection process)
Details of the moving object region detection process in the content superimposition display process will now be described. FIG. 4 is a flowchart showing a flow of detection processing of the moving object region.

  As described above, in the present embodiment, the control unit 11 detects the moving object region in consideration of the self-motion of the HMD 100 (changes in the postures of the cameras 16 and 17).

  As shown in the figure, the control unit 11 first calculates the depth and depth distribution in the Z direction in the real world for each pixel by performing matching between images from a plurality of viewpoints from the cameras 16 and 17 at the same time. (Step 41). The depth distribution corresponds to a so-called depth map.

  In addition, even when only one camera is used or when only one of the two cameras is used, the control unit 11 can use internal parameters (Intrinsic Parameters) such as the focal length of the camera, the size of the sensor, and the camera position / By performing projective transformation based on the direction parameter (Extrinsic Parameter), it is also possible to calculate where the subject and area corresponding to each pixel on the camera image are located in the real world three-dimensional space it can.

  Subsequently, the control unit 11 creates a point group (3D Point Cloud) in which the pixels on the Depth Map are mapped on the real-world three-dimensional space (Step 42).

  Subsequently, the control unit 11 calculates a self-motion amount (a three-dimensional position and angle fluctuation amount) from various sensor information of the sensor unit 14 such as the gyro sensor and the acceleration sensor (step 43). This self-momentum corresponds to the fluctuation of the extrinsic parameter in the frame following the frame in which the depth distribution is calculated.

  Subsequently, the control unit 11 projects the 3D Point Cloud calculated by the above-described method in the immediately preceding frame onto the camera placed at the position and angle in the self-momentum calculated from the sensor information to calculate the Depth Map. (Step 44).

  Subsequently, the control unit 11 calculates Depth Map in the same manner as described above in the next frame (step 45).

  Subsequently, the control unit 11 compares the depth map calculated in step 44 with the depth map calculated in step 45 in units of overlapping display candidate areas (step 46).

  If the object in the input image is a rigid body or a stationary object, the difference between the two depth maps should be almost zero. Therefore, when there is the difference (Yes in Step 47), the control unit 11 determines the area where the difference exists as a moving body area (Step 48).

  On the other hand, when there is no difference (No in Step 47), the control unit 11 determines that the superimposed display candidate area is not a moving object area (Step 49).

  Here, the control unit 11 can determine whether or not it is a moving object region in consideration of not only the depth but also the difference in luminance values.

  Similarly, the control unit 11 can detect the moving object region by sequentially performing the inter-frame comparison in time series.

  As described above, according to the present embodiment, the HMD 100 adaptively controls the position of the superimposed display so as to exclude the moving object region, the texture region, and the non-planar region from the display region according to the actual environment. Thus, visibility can be improved.

[Modification]
The present technology is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present technology.

  In the above-described embodiment, the moving object region, the texture region, and the non-planar region are all excluded from the superimposed display candidate regions, but any one or two of these three may be excluded conditions.

  For example, for the non-planar region, the HMD 100 may detect the non-planar shape, deform the content along the non-planar shape based on depth information or the like, and superimpose and display the content on the region. Good.

  Further, for example, the HMD 100 may dare to detect the moving object area as the superimposed display area from the input image. In this case, in consideration of safety, the HMD 100 may limit the moving object region to the superimposed display region only when the user is stationary.

  In the above-described embodiment, the HMD 100 detects whether the subject is a moving object in consideration of self-motion. However, in a glass-type wearable device such as the HMD100, the superimposed display is not performed in consideration of safety during the movement of the user, and the superimposed display is performed only when the user stops, thereby arousing the user's attention and gazing. A use case such as “Yes” is also conceivable.

  In this case, the HMD 100 may limit the moving object region detection process to the self-still state. Thereby, the detection process is simplified and the processing load is reduced.

  That is, the HMD 100 first detects a so-called self-stationary state where there is no self-momentum (posture is almost stationary) from the result of the measurement value of the gyro / acceleration sensor or the like. The HMD 100 can regard a pixel or region having a luminance difference as a moving object region only by taking a difference between time-series images on the premise that the self is stationary.

  In the above-described embodiment, an example in which a see-through glasses-type HMD having a stereo camera is applied to the present technology is shown, but the present technology is not limited to this.

  For example, a retina projector may be used for the display unit of a similar wearable device. Moreover, the same process as the above-mentioned embodiment may be implement | achieved by displaying the image imaged with cameras, such as a smart phone and a tablet, on a display part, and also displaying a content superimposed.

[Others]
The present technology can be configured as follows.
(1)
An imaging unit;
A candidate area that is a candidate for superimposed display of content is detected from the image captured by the imaging unit, and an area in which the undulation change of the luminance distribution is not more than a first threshold is detected as a superimposed display area among the candidate areas. A control unit configured to generate the content arranged so as to be virtually visually recognized on the superimposed display area;
An information processing apparatus comprising: an output unit configured to output the generated content superimposed on the superimposed display area.
(2)
The information processing apparatus according to (1) above,
The said control part detects the area | region where the undulation change of a three-dimensional shape is below a 2nd threshold value among the said candidate area | region as said superimposed display area.
(3)
The information processing apparatus according to (1) above,
The control unit detects whether or not the candidate area is a moving body area from the captured image, and excludes the moving body area from the superimposed display area.
(4)
The information processing apparatus according to (3) above,
A sensor configured to detect the attitude of the information processing apparatus;
The information processing apparatus, wherein the control unit detects a change in posture detected by the sensor and subtracts the change in posture from the captured image to detect the moving object region.
(5)
The information processing apparatus according to (4) above,
The control unit calculates a first depth distribution and a second depth distribution from the first and second consecutive images of the captured images, respectively, and the first image and the second image The third depth distribution is calculated by reflecting the variation amount of the posture detected in the time interval in the first depth distribution, and the presence / absence of a difference between the second depth distribution and the third depth distribution An information processing device that detects the presence or absence of the moving object region by detecting the motion.
(6)
The information processing apparatus according to (3) above,
A sensor configured to detect the attitude of the information processing apparatus;
The control unit determines whether or not the information processing apparatus is stationary based on the detection result of the sensor, and calculates a difference between the captured consecutive images when the information processing apparatus is stationary. An information processing apparatus that detects the moving object region by extracting.
(7)
The information processing apparatus according to (1) above,
The output unit superimposes the generated content on the superimposed display area in a semi-transparent state and outputs the superimposed content.
When the candidate area whose undulation change of the luminance distribution is not more than a first threshold is not detected, the control unit is configured to superimpose the generated content so that the transparency of the generated content is lower than that of the semi-transparent state. Information processing device that controls.
(8)
The information processing apparatus according to (1) above,
When the candidate area in which the undulation change of the luminance distribution is not more than a first threshold is not detected, the control unit determines that the content is changed to an area other than the candidate area, and the undulation change of the luminance distribution is greater than the first threshold. An information processing apparatus that controls the output unit to display in association with a large candidate area.
(9)
The information processing apparatus according to (1) above,
The control unit detects a moving body region as the superimposed display region from the captured image.

DESCRIPTION OF SYMBOLS 11 ... Control part 12 ... Memory | storage part 13 ... Communication part 14 ... Sensor part 15 ... Operation reception part 16 ... Right camera 17 ... Left camera 18 ... Display part 100 ... HMD (Head Mount Display)

Claims (11)

An imaging unit;
A candidate area that is a candidate for superimposed display of content is detected from the image captured by the imaging unit, and an area in which the undulation change of the luminance distribution is not more than a first threshold is detected as a superimposed display area among the candidate areas. A control unit configured to generate the content arranged so as to be virtually visually recognized on the superimposed display area;
An information processing apparatus comprising: an output unit configured to output the generated content superimposed on the superimposed display area. The information processing apparatus according to claim 1,
The said control part detects the area | region where the undulation change of a three-dimensional shape is below a 2nd threshold value among the said candidate area | region as said superimposed display area. The information processing apparatus according to claim 1,
The control unit detects whether or not the candidate area is a moving body area from the captured image, and excludes the moving body area from the superimposed display area. The information processing apparatus according to claim 3,
A sensor configured to detect the attitude of the information processing apparatus;
The information processing apparatus, wherein the control unit detects a change in posture detected by the sensor and subtracts the change in posture from the captured image to detect the moving object region. The information processing apparatus according to claim 4,
The control unit calculates a first depth distribution and a second depth distribution from the first and second consecutive images of the captured images, respectively, and the first image and the second image The third depth distribution is calculated by reflecting the variation amount of the posture detected in the time interval in the first depth distribution, and the presence / absence of a difference between the second depth distribution and the third depth distribution An information processing apparatus that detects the presence or absence of the moving object region by detecting a moving object region. The information processing apparatus according to claim 3,
A sensor configured to detect the attitude of the information processing apparatus;
The control unit determines whether or not the information processing apparatus is stationary based on the detection result of the sensor, and calculates a difference between the captured consecutive images when the information processing apparatus is stationary. An information processing apparatus that detects the moving object region by extracting. The information processing apparatus according to claim 1,
The output unit superimposes the generated content on the superimposed display area in a semi-transparent state and outputs the superimposed content.
When the candidate area whose undulation change of the luminance distribution is not more than a first threshold is not detected, the control unit is configured to superimpose the generated content so that the transparency of the generated content is lower than that of the semi-transparent state. Information processing device that controls. The information processing apparatus according to claim 1,
When the candidate area in which the undulation change of the luminance distribution is not more than a first threshold is not detected, the control unit determines that the content is changed to an area other than the candidate area, and the undulation change of the luminance distribution is greater than the first threshold. An information processing apparatus that controls the output unit to display in association with a large candidate area. The information processing apparatus according to claim 1,
The control unit detects a moving body region as the superimposed display region from the captured image. A candidate region that is a candidate for superimposed display of content is detected from an image captured by the imaging device;
Among the detected candidate areas, an area where the undulation change of the luminance distribution is a predetermined threshold value or less is detected as a superimposed display area,
Generating the content arranged to be virtually visually recognized on the superimposed display area by the user,
An information processing apparatus that outputs the generated content superimposed on the superimposed display area. In the information processing device,
Detecting a candidate region that is a candidate for superimposed display of content from an image captured by an imaging device;
Detecting a region where the undulation change of the luminance distribution is not more than a predetermined threshold among the detected candidate regions as a superimposed display region;
Generating the content arranged to be virtually viewed on the superimposed display area by a user;
A program for executing the step of outputting the generated content superimposed on the superimposed display area.

Images